A comprehensive review of the video-to-text problem
- 16 January 2022
- journal article
- review article
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 55 (5) , 4165-4239
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Agencia Nacional de Investigación y Desarrollo de Chile (ANID/Doctorado Nacional/2018-21180648)
This publication has 167 references indexed in Scilit:
- Understanding temporal structure for video captioningPattern Analysis and Applications, 2019
- ECO: Efficient Convolutional Network for Online Video Understanding2018
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification2018
- Less Is More: Picking Informative Frames for Video Captioning2018
- Con-S2V: A Generic Framework for Incorporating Extra-Sentential Context into Sen2Vec2017
- SSD: Single Shot MultiBox Detector2016
- Title Generation for User Generated Videos2016
- SPICE: Semantic Propositional Image Caption Evaluation2016
- The Long-Short Story of Movie Description2015
- Coherent Multi-sentence Video Description with Variable Level of Detail2014